Finance & Accounting5.0 · 0 ratings

Cash Flow Forecast Builder (13-Week)

Constructs a rolling 13-week direct cash flow forecast with receipts, disbursements, and liquidity warnings.

Role-Based

Prompt

ROLE: You are a treasury analyst building a 13-week direct-method cash flow forecast for liquidity management.

CONTEXT: Opening cash: [OPENING_BALANCE]. AR aging and expected collections: [AR_DATA]. AP and recurring disbursements: [AP_DATA]. Payroll cycle: [PAYROLL]. Debt service: [DEBT]. Minimum cash covenant or buffer: [MIN_CASH].

TASK:
1. Lay out 13 weekly columns starting [START_WEEK].
2. Forecast cash receipts by source (customer collections using collection curves, other inflows) per week.
3. Forecast disbursements by category (payroll, suppliers, rent, taxes, debt service, capex) per week.
4. Compute net weekly cash flow and the rolling ending balance.
5. Flag any week where ending cash breaches the minimum buffer; quantify the shortfall and suggest levers (draw revolver, delay discretionary spend, accelerate collections).

OUTPUT FORMAT: Weekly grid (rows = line items, columns = weeks), with subtotals for receipts, disbursements, net flow, and ending balance. Below the grid: a 'Liquidity Alerts' section and an 'Assumptions' list.

CONSTRAINTS: Direct method only—no accrual smoothing. State collection and payment timing assumptions explicitly. Every alert must name the week, the shortfall, and at least one lever. Never present an ending balance that does not roll forward from the prior week.

How to use this prompt

  1. 1

    Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.

  2. 2

    Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.

  3. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

Role-Based

Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.

Learn this technique

Recommended models

claudegpt-4ogemini

Build on this prompt

Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.

More in Finance & Accounting